Sato Saga

Vector quantization of images with variable block size

We proposed a vector quantization (VQ) with variable block size using local fractal dimensions (LFDs) of an image. A VQ with variable block size has so far been implemented using a quad tree (QT) decomposition algorithm. QT decomposition carries out image partitioning based on the homogeneity of local regions of an image. However, we think that the complexity of local regions of an image is more essential than the homogeneity, because we pay close attention to complex region than homogeneous region. Therefore, complex regions are essential for image compression. Since the complexity of regions of an image is quantified by values of LFD, we implemented variable block size using LFD values and constructed a codebook (CB) for a VQ. To confirm the performance of the proposed method, we only used a discriminant analysis and FGLA to construct a CB. Here, the FGLA is the algorithm to combine generalized Lloyd algorithm (GLA) and the fuzzy k means algorithm. Results of computational experiments showed that this method correctly encodes the regions that we pay close attention. This is a promising result for obtaining a well-perceived compressed image. Also, the performance of the proposed method is superior to that of VQ by FGLA in terms of both compression rate and decoded image quality. Furthermore, 1.0bpp and more than 30dB in PSNR by a CB with only 252 code-vectors were achieved using this method.

Rough and accurate segmentation of natural images using fuzzy region-growing algorithm

We present a rough and an accurate segmentation of natural images using a fuzzy region-growing algorithm. First, an optimum number of the blanket for local areas is determined to estimate the optimal local fractal dimension. Then, the intensity features and the local fractal-dimension feature are integrated into the fuzzy region-growing algorithm. In the proposed method, the intensity features are used to produce an accurate segmentation, while the fractal-dimension feature is used to yield a rough segmentation in a natural image. The effectiveness of the proposed method is confirmed through computer simulations that demonstrate a rough segmentation at the fine-texture regions and an accurate segmentation at the strong-edge regions simultaneously.

Fuzzy region-growing segmentation of natural images using local fractal dimension

We present a new method that integrates intensity features and a local fractal-dimension feature into a region growing algorithm for the segmentation of natural images. A fuzzy rule is used to integrate different type of feature into a segmentation algorithm. In the proposed algorithm, intensity features are used to produce an accurate segmentation, while the fractal-dimension feature is used to yield a rough segmentation in a natural image. The effective combination of the different features provides the segmented results similar to the ones by a human visual system.

A method for modeling freehand curves : the fuzzy spline interpolation

In this paper, a fuzzy spline interpolation technique is proposed to give a fuzzy model of sampled freehand curves that involve vagueness (associated with roughness is drawing) in their positional information. The fuzzy model is an extension of ordinary spline curves. Because the model inherits geometric characteristics from spline curves and can be handled as a fuzzy set, it provides a fuzzy inference approach to the geometric meaning of the drawers original intention, allowing for the vagueness of the drawn freehand curves. An application of the model to freehand curve segmentation demonstrates the necessity of the method.

Signal processing and pattern recognition with soft computing

We describe the overall role of soft computing (SC) in signal processing and pattern recognition (SPPR) with specific applications to biomedical engineering, geoscience for mining and civil engineering human interfaces, and image processing. Detection of characteristic points in an electrocardiogram to implement an advanced ECG analyzer is presented which is carried out using both conventional SPPR techniques and self-organizing neural networks. Successful technologies for monitoring a geostructure by supervised and self-organizing neural networks are described. Identification of a freehand drawing by a combination of fuzzy logic and neural networks is also described. Moreover, application of fuzzy logic to image segmentation is presented. Finally, innovation of SPPR using SC technologies is discussed.

Unsupervised perceptual segmentation of natural color images using fuzzy-based hierarchical algorithm

This paper proposes unsupervised perceptual segmentation of natural color images using a fuzzy-based hierarchical algorithm. L*a*b* color space is used to represent color features and statistical geometrical features are adopted as texture features. A fuzzy-based homogeneity measure makes a fusion of color features and texture features. Proposed hierarchical segmentation method is performed in four stages: simple splitting, local merging, global merging and boundary refinement. Experiments on segmentation of natural color images are presented to verify the effectiveness of the proposed method in obtaining perceptual segmentation.

Number-Driven Perceptual Segmentation of Natural Color Images for Easy Decision of Optimal Result

This paper proposes number-driven perceptual segmentation of natural color images using a fuzzy-based hierarchical algorithm for an easy decision of the optimal segmentation result. A fuzzy-based homogeneity measure makes a fusion of the L*a*b* color features and the SGF texture features. Proposed hierarchical segmentation method is performed in four stages: simple splitting, local merging, global merging and boundary refinement. The effectiveness of the proposed method is confirmed through computer simulations that demonstrate an easy determination of the optimal segmentation result.

General Parameter Radial Basis Function Neural Network Based Adaptive Fuzzy Systems

In this paper an automatic fuzzy rule generation problem through the artificial neural network (ANN) approach is considered. The unknown fuzzy relation reconstruction problem is treated as an optimization of the structure and parameters of the neural network. The functional equivalence between some classes of fuzzy systems and radial basis function networks (RBFNs), namely, their localized sensitivity to input value, is a background of the proposed approach. The improved structure and advanced learning feature RBFN is developed based on General Parameter (GP) method of complex system identification. The criterion of the GP RBFN (General Parameter Radial Basis Function Network) structure optimality is derived using the GP steady state statistics. The derived criterion is used then for the development of the GP RBFN structure self-organization procedure. As a result, an Adaptive Fuzzy System (AFS) with capability to extract fuzzy If-Then rules from input and output sample data is proposed. Simulation examples are given.

Fuzzy Vector Quantization of Images Based on Local Fractal Dimensions

Telecommunication networks are spreading worldwide. People can communicate with each other beyond spacial restrictions using the Internet. In this situation, the demand for transmission bandwidth and storage space continues to outstrip the capacity of existing technologies. Image and video compression technology is therefore essential for the effective use of communication networks. In this paper, we propose a new method to compress images using vector quantization. Dimensions of the training vectors to prepare a codebook are determined on the basis of local fractal dimensions (LFDs) of a learning image. This means that each block size to divide the learning image is specified by the LFDs. In principle, the smaller the number of pixels in a training vector is, the larger is a codebook (low bit rate). Furthermore, the smaller the number of pixels in a codebook is, the higher is the quality of the encoded image. This is a tradeoff between compression rate and quality of the encoded image. The tradeoff can be solved by the division of images with different block sizes. Furthermore, the code-vectors are computed from the training vectors using a fuzzy k-means clustering algorithm. The performance of the proposed algorithm was evaluated by compression rate and quality of encoded images in comparison with those using fuzzy generalized Lloyd algorithm. The experiments showed that the proposed algorithm solved the tradeoff between compression rate and quality of image.

Vector quantization of images using fractal dimensions

In conventional vector quantization (VQ), for example, generalized Lloyd algorithm (GLA), an image is divided into blocks that are all the same size. This uniform division could be redundant. Furthermore, it could not attain both a high compression rate and high quality of encoded image. We propose a new method of VQ in which the block size to divide an image is determined by a local fractal dimension (LDF). Computational experiments were carried out to show the effectiveness of the method. Results of experiments showed that a compression rate of the proposed method is higher than that by the GLA under the condition that PSNR (Peak Signal-to-Noise Ratio) is more than 35.0 dB. Therefore, the proposed method is useful for practical image compression.